Finished training
Browse files- all_results.json +13 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/May11_21-21-57_r5u27n1.puma.hpc.arizona.edu/events.out.tfevents.1652329346.r5u27n1.puma.hpc.arizona.edu.76190.0 +2 -2
- runs/May11_21-21-57_r5u27n1.puma.hpc.arizona.edu/events.out.tfevents.1652334887.r5u27n1.puma.hpc.arizona.edu.76190.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +541 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.28,
|
| 3 |
+
"eval_accuracy": 0.38079066527342387,
|
| 4 |
+
"eval_loss": 3.901303291320801,
|
| 5 |
+
"eval_runtime": 16.4247,
|
| 6 |
+
"eval_samples_per_second": 608.84,
|
| 7 |
+
"eval_steps_per_second": 19.057,
|
| 8 |
+
"perplexity": 49.46687686362511,
|
| 9 |
+
"train_loss": 3.4590183206506677,
|
| 10 |
+
"train_runtime": 5524.5303,
|
| 11 |
+
"train_samples_per_second": 332.471,
|
| 12 |
+
"train_steps_per_second": 0.041
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.28,
|
| 3 |
+
"eval_accuracy": 0.38079066527342387,
|
| 4 |
+
"eval_loss": 3.901303291320801,
|
| 5 |
+
"eval_runtime": 16.4247,
|
| 6 |
+
"eval_samples_per_second": 608.84,
|
| 7 |
+
"eval_steps_per_second": 19.057,
|
| 8 |
+
"perplexity": 49.46687686362511
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438128811
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a2225bf84c7db72a9f66afe9c35bb4b82f397a2bffd4dbda6972fb9f7aca431
|
| 3 |
size 438128811
|
runs/May11_21-21-57_r5u27n1.puma.hpc.arizona.edu/events.out.tfevents.1652329346.r5u27n1.puma.hpc.arizona.edu.76190.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a98c1faaeffe6b378b8eae71d0c38e54540cf5e55e0c591c5ee5955b1dfa980
|
| 3 |
+
size 20127
|
runs/May11_21-21-57_r5u27n1.puma.hpc.arizona.edu/events.out.tfevents.1652334887.r5u27n1.puma.hpc.arizona.edu.76190.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3d8514881a3f70c0ed42eb996e1d5a1691daee45de993e85a8f2611adbb74d5
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.28,
|
| 3 |
+
"train_loss": 3.4590183206506677,
|
| 4 |
+
"train_runtime": 5524.5303,
|
| 5 |
+
"train_samples_per_second": 332.471,
|
| 6 |
+
"train_steps_per_second": 0.041
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.38235806339254613,
|
| 3 |
+
"best_model_checkpoint": "/groups/claytonm/enoriega/kw_pubmed/kw_pubmed_1000_0.000006/checkpoint-108",
|
| 4 |
+
"epoch": 3.283101045296167,
|
| 5 |
+
"global_step": 148,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"eval_accuracy": 0.36533437826541276,
|
| 13 |
+
"eval_loss": 4.0918426513671875,
|
| 14 |
+
"eval_runtime": 16.5878,
|
| 15 |
+
"eval_samples_per_second": 602.854,
|
| 16 |
+
"eval_steps_per_second": 18.869,
|
| 17 |
+
"step": 4
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.11,
|
| 21 |
+
"learning_rate": 5.92e-06,
|
| 22 |
+
"loss": 4.4572,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17,
|
| 27 |
+
"eval_accuracy": 0.36964472309299895,
|
| 28 |
+
"eval_loss": 4.006958961486816,
|
| 29 |
+
"eval_runtime": 16.4206,
|
| 30 |
+
"eval_samples_per_second": 608.992,
|
| 31 |
+
"eval_steps_per_second": 19.061,
|
| 32 |
+
"step": 8
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 5.786666666666667e-06,
|
| 37 |
+
"loss": 4.0734,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.26,
|
| 42 |
+
"eval_accuracy": 0.37338906304423547,
|
| 43 |
+
"eval_loss": 3.9496026039123535,
|
| 44 |
+
"eval_runtime": 16.513,
|
| 45 |
+
"eval_samples_per_second": 605.585,
|
| 46 |
+
"eval_steps_per_second": 18.955,
|
| 47 |
+
"step": 12
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.33,
|
| 51 |
+
"learning_rate": 5.653333333333333e-06,
|
| 52 |
+
"loss": 3.8884,
|
| 53 |
+
"step": 15
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.35,
|
| 57 |
+
"eval_accuracy": 0.37656739811912227,
|
| 58 |
+
"eval_loss": 3.918774127960205,
|
| 59 |
+
"eval_runtime": 16.5065,
|
| 60 |
+
"eval_samples_per_second": 605.823,
|
| 61 |
+
"eval_steps_per_second": 18.962,
|
| 62 |
+
"step": 16
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"learning_rate": 5.5200000000000005e-06,
|
| 67 |
+
"loss": 3.8037,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.44,
|
| 72 |
+
"eval_accuracy": 0.37495646116335773,
|
| 73 |
+
"eval_loss": 3.9296493530273438,
|
| 74 |
+
"eval_runtime": 16.4773,
|
| 75 |
+
"eval_samples_per_second": 606.897,
|
| 76 |
+
"eval_steps_per_second": 18.996,
|
| 77 |
+
"step": 20
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.52,
|
| 81 |
+
"eval_accuracy": 0.37891849529780564,
|
| 82 |
+
"eval_loss": 3.903676748275757,
|
| 83 |
+
"eval_runtime": 16.4879,
|
| 84 |
+
"eval_samples_per_second": 606.507,
|
| 85 |
+
"eval_steps_per_second": 18.984,
|
| 86 |
+
"step": 24
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.54,
|
| 90 |
+
"learning_rate": 5.386666666666667e-06,
|
| 91 |
+
"loss": 3.7326,
|
| 92 |
+
"step": 25
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.61,
|
| 96 |
+
"eval_accuracy": 0.3787878787878788,
|
| 97 |
+
"eval_loss": 3.8809974193573,
|
| 98 |
+
"eval_runtime": 16.5092,
|
| 99 |
+
"eval_samples_per_second": 605.724,
|
| 100 |
+
"eval_steps_per_second": 18.959,
|
| 101 |
+
"step": 28
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.65,
|
| 105 |
+
"learning_rate": 5.2533333333333336e-06,
|
| 106 |
+
"loss": 3.6766,
|
| 107 |
+
"step": 30
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7,
|
| 111 |
+
"eval_accuracy": 0.3770463253221874,
|
| 112 |
+
"eval_loss": 3.8815793991088867,
|
| 113 |
+
"eval_runtime": 16.4832,
|
| 114 |
+
"eval_samples_per_second": 606.677,
|
| 115 |
+
"eval_steps_per_second": 18.989,
|
| 116 |
+
"step": 32
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.76,
|
| 120 |
+
"learning_rate": 5.12e-06,
|
| 121 |
+
"loss": 3.6152,
|
| 122 |
+
"step": 35
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.78,
|
| 126 |
+
"eval_accuracy": 0.3797892720306513,
|
| 127 |
+
"eval_loss": 3.8686890602111816,
|
| 128 |
+
"eval_runtime": 16.4735,
|
| 129 |
+
"eval_samples_per_second": 607.035,
|
| 130 |
+
"eval_steps_per_second": 19.0,
|
| 131 |
+
"step": 36
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.87,
|
| 135 |
+
"learning_rate": 4.986666666666667e-06,
|
| 136 |
+
"loss": 3.6143,
|
| 137 |
+
"step": 40
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.87,
|
| 141 |
+
"eval_accuracy": 0.3770463253221874,
|
| 142 |
+
"eval_loss": 3.874457597732544,
|
| 143 |
+
"eval_runtime": 16.4674,
|
| 144 |
+
"eval_samples_per_second": 607.26,
|
| 145 |
+
"eval_steps_per_second": 19.007,
|
| 146 |
+
"step": 40
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.96,
|
| 150 |
+
"eval_accuracy": 0.3777429467084639,
|
| 151 |
+
"eval_loss": 3.872670888900757,
|
| 152 |
+
"eval_runtime": 16.447,
|
| 153 |
+
"eval_samples_per_second": 608.012,
|
| 154 |
+
"eval_steps_per_second": 19.031,
|
| 155 |
+
"step": 44
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.98,
|
| 159 |
+
"learning_rate": 4.853333333333333e-06,
|
| 160 |
+
"loss": 3.54,
|
| 161 |
+
"step": 45
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.07,
|
| 165 |
+
"eval_accuracy": 0.3747387669801463,
|
| 166 |
+
"eval_loss": 3.882456064224243,
|
| 167 |
+
"eval_runtime": 16.5148,
|
| 168 |
+
"eval_samples_per_second": 605.517,
|
| 169 |
+
"eval_steps_per_second": 18.953,
|
| 170 |
+
"step": 48
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.11,
|
| 174 |
+
"learning_rate": 4.72e-06,
|
| 175 |
+
"loss": 4.1293,
|
| 176 |
+
"step": 50
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.15,
|
| 180 |
+
"eval_accuracy": 0.38079066527342387,
|
| 181 |
+
"eval_loss": 3.8683102130889893,
|
| 182 |
+
"eval_runtime": 16.4717,
|
| 183 |
+
"eval_samples_per_second": 607.102,
|
| 184 |
+
"eval_steps_per_second": 19.002,
|
| 185 |
+
"step": 52
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.22,
|
| 189 |
+
"learning_rate": 4.586666666666667e-06,
|
| 190 |
+
"loss": 3.4379,
|
| 191 |
+
"step": 55
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.24,
|
| 195 |
+
"eval_accuracy": 0.37983281086729365,
|
| 196 |
+
"eval_loss": 3.8646554946899414,
|
| 197 |
+
"eval_runtime": 16.4967,
|
| 198 |
+
"eval_samples_per_second": 606.182,
|
| 199 |
+
"eval_steps_per_second": 18.973,
|
| 200 |
+
"step": 56
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.33,
|
| 204 |
+
"learning_rate": 4.453333333333334e-06,
|
| 205 |
+
"loss": 3.4215,
|
| 206 |
+
"step": 60
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.33,
|
| 210 |
+
"eval_accuracy": 0.3801375827237896,
|
| 211 |
+
"eval_loss": 3.8663816452026367,
|
| 212 |
+
"eval_runtime": 16.4695,
|
| 213 |
+
"eval_samples_per_second": 607.185,
|
| 214 |
+
"eval_steps_per_second": 19.005,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.41,
|
| 219 |
+
"eval_accuracy": 0.3804858934169279,
|
| 220 |
+
"eval_loss": 3.8687705993652344,
|
| 221 |
+
"eval_runtime": 16.462,
|
| 222 |
+
"eval_samples_per_second": 607.461,
|
| 223 |
+
"eval_steps_per_second": 19.014,
|
| 224 |
+
"step": 64
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.44,
|
| 228 |
+
"learning_rate": 4.32e-06,
|
| 229 |
+
"loss": 3.3448,
|
| 230 |
+
"step": 65
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.5,
|
| 234 |
+
"eval_accuracy": 0.38140020898641586,
|
| 235 |
+
"eval_loss": 3.876781463623047,
|
| 236 |
+
"eval_runtime": 16.4781,
|
| 237 |
+
"eval_samples_per_second": 606.866,
|
| 238 |
+
"eval_steps_per_second": 18.995,
|
| 239 |
+
"step": 68
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.54,
|
| 243 |
+
"learning_rate": 4.186666666666667e-06,
|
| 244 |
+
"loss": 3.3324,
|
| 245 |
+
"step": 70
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.59,
|
| 249 |
+
"eval_accuracy": 0.37717694183211425,
|
| 250 |
+
"eval_loss": 3.913390636444092,
|
| 251 |
+
"eval_runtime": 16.4943,
|
| 252 |
+
"eval_samples_per_second": 606.268,
|
| 253 |
+
"eval_steps_per_second": 18.976,
|
| 254 |
+
"step": 72
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.65,
|
| 258 |
+
"learning_rate": 4.053333333333333e-06,
|
| 259 |
+
"loss": 3.3088,
|
| 260 |
+
"step": 75
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.68,
|
| 264 |
+
"eval_accuracy": 0.3799634273772205,
|
| 265 |
+
"eval_loss": 3.882460832595825,
|
| 266 |
+
"eval_runtime": 16.4932,
|
| 267 |
+
"eval_samples_per_second": 606.311,
|
| 268 |
+
"eval_steps_per_second": 18.978,
|
| 269 |
+
"step": 76
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.76,
|
| 273 |
+
"learning_rate": 3.92e-06,
|
| 274 |
+
"loss": 3.2765,
|
| 275 |
+
"step": 80
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.76,
|
| 279 |
+
"eval_accuracy": 0.37787356321839083,
|
| 280 |
+
"eval_loss": 3.8959219455718994,
|
| 281 |
+
"eval_runtime": 16.5043,
|
| 282 |
+
"eval_samples_per_second": 605.902,
|
| 283 |
+
"eval_steps_per_second": 18.965,
|
| 284 |
+
"step": 80
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.85,
|
| 288 |
+
"eval_accuracy": 0.37913618948101707,
|
| 289 |
+
"eval_loss": 3.9021382331848145,
|
| 290 |
+
"eval_runtime": 16.4868,
|
| 291 |
+
"eval_samples_per_second": 606.546,
|
| 292 |
+
"eval_steps_per_second": 18.985,
|
| 293 |
+
"step": 84
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.87,
|
| 297 |
+
"learning_rate": 3.7866666666666667e-06,
|
| 298 |
+
"loss": 3.2439,
|
| 299 |
+
"step": 85
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.94,
|
| 303 |
+
"eval_accuracy": 0.38148728665970044,
|
| 304 |
+
"eval_loss": 3.8731861114501953,
|
| 305 |
+
"eval_runtime": 16.4672,
|
| 306 |
+
"eval_samples_per_second": 607.269,
|
| 307 |
+
"eval_steps_per_second": 19.008,
|
| 308 |
+
"step": 88
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.98,
|
| 312 |
+
"learning_rate": 3.6533333333333336e-06,
|
| 313 |
+
"loss": 3.2546,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.04,
|
| 318 |
+
"eval_accuracy": 0.38044235458028564,
|
| 319 |
+
"eval_loss": 3.8909058570861816,
|
| 320 |
+
"eval_runtime": 16.4399,
|
| 321 |
+
"eval_samples_per_second": 608.277,
|
| 322 |
+
"eval_steps_per_second": 19.039,
|
| 323 |
+
"step": 92
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.11,
|
| 327 |
+
"learning_rate": 3.52e-06,
|
| 328 |
+
"loss": 3.818,
|
| 329 |
+
"step": 95
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.13,
|
| 333 |
+
"eval_accuracy": 0.3787443399512365,
|
| 334 |
+
"eval_loss": 3.917863368988037,
|
| 335 |
+
"eval_runtime": 16.4722,
|
| 336 |
+
"eval_samples_per_second": 607.083,
|
| 337 |
+
"eval_steps_per_second": 19.002,
|
| 338 |
+
"step": 96
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.22,
|
| 342 |
+
"learning_rate": 3.3866666666666667e-06,
|
| 343 |
+
"loss": 3.1567,
|
| 344 |
+
"step": 100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.22,
|
| 348 |
+
"eval_accuracy": 0.3803988157436433,
|
| 349 |
+
"eval_loss": 3.906223773956299,
|
| 350 |
+
"eval_runtime": 16.5109,
|
| 351 |
+
"eval_samples_per_second": 605.66,
|
| 352 |
+
"eval_steps_per_second": 18.957,
|
| 353 |
+
"step": 100
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.3,
|
| 357 |
+
"eval_accuracy": 0.3793974225008708,
|
| 358 |
+
"eval_loss": 3.9190924167633057,
|
| 359 |
+
"eval_runtime": 16.4677,
|
| 360 |
+
"eval_samples_per_second": 607.249,
|
| 361 |
+
"eval_steps_per_second": 19.007,
|
| 362 |
+
"step": 104
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.33,
|
| 366 |
+
"learning_rate": 3.2533333333333337e-06,
|
| 367 |
+
"loss": 3.1563,
|
| 368 |
+
"step": 105
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.39,
|
| 372 |
+
"eval_accuracy": 0.38235806339254613,
|
| 373 |
+
"eval_loss": 3.8962931632995605,
|
| 374 |
+
"eval_runtime": 16.4504,
|
| 375 |
+
"eval_samples_per_second": 607.888,
|
| 376 |
+
"eval_steps_per_second": 19.027,
|
| 377 |
+
"step": 108
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.44,
|
| 381 |
+
"learning_rate": 3.12e-06,
|
| 382 |
+
"loss": 3.1417,
|
| 383 |
+
"step": 110
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.48,
|
| 387 |
+
"eval_accuracy": 0.37948450017415536,
|
| 388 |
+
"eval_loss": 3.924445152282715,
|
| 389 |
+
"eval_runtime": 16.4336,
|
| 390 |
+
"eval_samples_per_second": 608.508,
|
| 391 |
+
"eval_steps_per_second": 19.046,
|
| 392 |
+
"step": 112
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.54,
|
| 396 |
+
"learning_rate": 2.9866666666666667e-06,
|
| 397 |
+
"loss": 3.1247,
|
| 398 |
+
"step": 115
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.57,
|
| 402 |
+
"eval_accuracy": 0.3790055729710902,
|
| 403 |
+
"eval_loss": 3.9178736209869385,
|
| 404 |
+
"eval_runtime": 16.4751,
|
| 405 |
+
"eval_samples_per_second": 606.976,
|
| 406 |
+
"eval_steps_per_second": 18.998,
|
| 407 |
+
"step": 116
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.65,
|
| 411 |
+
"learning_rate": 2.8533333333333333e-06,
|
| 412 |
+
"loss": 3.1307,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.65,
|
| 417 |
+
"eval_accuracy": 0.3778300243817485,
|
| 418 |
+
"eval_loss": 3.939385175704956,
|
| 419 |
+
"eval_runtime": 16.4922,
|
| 420 |
+
"eval_samples_per_second": 606.346,
|
| 421 |
+
"eval_steps_per_second": 18.979,
|
| 422 |
+
"step": 120
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.74,
|
| 426 |
+
"eval_accuracy": 0.38179205851619646,
|
| 427 |
+
"eval_loss": 3.9248249530792236,
|
| 428 |
+
"eval_runtime": 16.503,
|
| 429 |
+
"eval_samples_per_second": 605.949,
|
| 430 |
+
"eval_steps_per_second": 18.966,
|
| 431 |
+
"step": 124
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.76,
|
| 435 |
+
"learning_rate": 2.72e-06,
|
| 436 |
+
"loss": 3.0893,
|
| 437 |
+
"step": 125
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.83,
|
| 441 |
+
"eval_accuracy": 0.37752525252525254,
|
| 442 |
+
"eval_loss": 3.94762921333313,
|
| 443 |
+
"eval_runtime": 16.4815,
|
| 444 |
+
"eval_samples_per_second": 606.74,
|
| 445 |
+
"eval_steps_per_second": 18.991,
|
| 446 |
+
"step": 128
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.87,
|
| 450 |
+
"learning_rate": 2.5866666666666667e-06,
|
| 451 |
+
"loss": 3.0906,
|
| 452 |
+
"step": 130
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.91,
|
| 456 |
+
"eval_accuracy": 0.3811825148032045,
|
| 457 |
+
"eval_loss": 3.9266726970672607,
|
| 458 |
+
"eval_runtime": 16.4398,
|
| 459 |
+
"eval_samples_per_second": 608.279,
|
| 460 |
+
"eval_steps_per_second": 19.039,
|
| 461 |
+
"step": 132
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.98,
|
| 465 |
+
"learning_rate": 2.4533333333333337e-06,
|
| 466 |
+
"loss": 3.0575,
|
| 467 |
+
"step": 135
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.02,
|
| 471 |
+
"eval_accuracy": 0.37813479623824453,
|
| 472 |
+
"eval_loss": 3.937913417816162,
|
| 473 |
+
"eval_runtime": 16.4796,
|
| 474 |
+
"eval_samples_per_second": 606.812,
|
| 475 |
+
"eval_steps_per_second": 18.993,
|
| 476 |
+
"step": 136
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.11,
|
| 480 |
+
"learning_rate": 2.32e-06,
|
| 481 |
+
"loss": 3.6148,
|
| 482 |
+
"step": 140
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.11,
|
| 486 |
+
"eval_accuracy": 0.3803988157436433,
|
| 487 |
+
"eval_loss": 3.9217216968536377,
|
| 488 |
+
"eval_runtime": 16.4193,
|
| 489 |
+
"eval_samples_per_second": 609.04,
|
| 490 |
+
"eval_steps_per_second": 19.063,
|
| 491 |
+
"step": 140
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.2,
|
| 495 |
+
"eval_accuracy": 0.37861372344130967,
|
| 496 |
+
"eval_loss": 3.934666156768799,
|
| 497 |
+
"eval_runtime": 16.4991,
|
| 498 |
+
"eval_samples_per_second": 606.093,
|
| 499 |
+
"eval_steps_per_second": 18.971,
|
| 500 |
+
"step": 144
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.22,
|
| 504 |
+
"learning_rate": 2.1866666666666668e-06,
|
| 505 |
+
"loss": 3.035,
|
| 506 |
+
"step": 145
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.28,
|
| 510 |
+
"eval_accuracy": 0.37944096133751304,
|
| 511 |
+
"eval_loss": 3.9348745346069336,
|
| 512 |
+
"eval_runtime": 16.4542,
|
| 513 |
+
"eval_samples_per_second": 607.749,
|
| 514 |
+
"eval_steps_per_second": 19.023,
|
| 515 |
+
"step": 148
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.28,
|
| 519 |
+
"step": 148,
|
| 520 |
+
"total_flos": 9.09876408404562e+16,
|
| 521 |
+
"train_loss": 3.4590183206506677,
|
| 522 |
+
"train_runtime": 5524.5303,
|
| 523 |
+
"train_samples_per_second": 332.471,
|
| 524 |
+
"train_steps_per_second": 0.041
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.28,
|
| 528 |
+
"eval_accuracy": 0.38079066527342387,
|
| 529 |
+
"eval_loss": 3.901303291320801,
|
| 530 |
+
"eval_runtime": 16.4247,
|
| 531 |
+
"eval_samples_per_second": 608.84,
|
| 532 |
+
"eval_steps_per_second": 19.057,
|
| 533 |
+
"step": 148
|
| 534 |
+
}
|
| 535 |
+
],
|
| 536 |
+
"max_steps": 225,
|
| 537 |
+
"num_train_epochs": 5,
|
| 538 |
+
"total_flos": 9.09876408404562e+16,
|
| 539 |
+
"trial_name": null,
|
| 540 |
+
"trial_params": null
|
| 541 |
+
}
|